Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0385. Min Range: -4.0385

Max Act: 4.0385. Min Act: -0.0000

Data Index: 262884 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.3833. Min Act: -0.0000

Data Index: 1011260 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.4898. Min Act: -0.0000

Data Index: 475764 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.2873. Min Act: -0.0000

Data Index: 1132553 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.1218. Min Act: -0.0000

Data Index: 265236 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.0382. Min Act: -0.0000

Data Index: 494311 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.1561. Min Act: -0.0000

Data Index: 1347439 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.1535. Min Act: -0.0000

Data Index: 57024 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.1260. Min Act: -0.0000

Data Index: 859030 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.2541. Min Act: -0.0000

Data Index: 1147445 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 4.0385. Min Range: -4.0385

Max Act: 2.8989. Min Act: -0.0000

Data Index: 146346 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.0127. Min Act: -0.0000

Data Index: 916376 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 4.0385. Min Range: -4.0385

Max Act: 2.8859. Min Act: -0.0000

Data Index: 81699 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.0577. Min Act: -0.0000

Data Index: 1174659 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.0534. Min Act: -0.0000

Data Index: 946006 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 4.0385. Min Range: -4.0385

Max Act: 2.8982. Min Act: -0.0000

Data Index: 580378 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 4.0385. Min Range: -4.0385

Max Act: 2.9148. Min Act: -0.0000

Data Index: 931073 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 4.0385. Min Range: -4.0385

Max Act: 3.0469. Min Act: -0.0000

Data Index: 1267984 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 4.0385. Min Range: -4.0385

Max Act: 2.8896. Min Act: -0.0000

Data Index: 964506 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 4.0385. Min Range: -4.0385

Max Act: 2.7544. Min Act: -0.0000

Data Index: 990901 (C4 (Web Text))

Max Activating Token Index: 636